OSU Natural Language Processing

All

58 repositories

saev
Public
Sparse autoencoders for vision
Elm
•
MIT License
•6•38•3•1•Updated Aug 1, 2025Aug 1, 2025
Explorer
Public
[ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
machine-learning synthetic-dataset-generation web-agents gui-agents
Python
•
MIT License
•0•12•1•0•Updated Jul 29, 2025Jul 29, 2025
WebGuard
Public
WebGuard: Building a Generalizable Guardrail for Web Agents
Python
•
MIT License
•0•6•0•0•Updated Jul 28, 2025Jul 28, 2025
Online-Mind2Web
Public
An Illusion of Progress? Assessing the Current State of Web Agents
Python
•
MIT License
•1•74•1•0•Updated Jul 22, 2025Jul 22, 2025
GrokkedTransformer
Public
Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
Python
•
MIT License
•24•225•3•0•Updated Jul 19, 2025Jul 19, 2025
Mind2Web-2
Public
Mind2Web-2 Benchmark: Evaluating Agentic Search with Agent-as-a-Judge
benchmark dataset agents cua webagent
Python
•
MIT License
•6•63•0•0•Updated Jul 19, 2025Jul 19, 2025
UGround
Public
[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents
artificial-intelligence web-agents gui-agents
Python
•
MIT License
•12•262•5•0•Updated Jul 18, 2025Jul 18, 2025
AutoSDT
Public
AutoSDT is a fully automatic pipeline to collect data-driven scientific coding tasks to train co-scientist models.
bioinformatics neuroscience computational-chemistry psychology geographical-information-system ai4science scientific-code
Python
•
MIT License
•0•10•0•0•Updated Jun 29, 2025Jun 29, 2025
GUI-Agents-Paper-List
Public
Building a comprehensive and handy list of papers for GUI agents
Python
•25•449•3•0•Updated Jun 27, 2025Jun 27, 2025
RedTeamCUA
Public
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
Python
•
Apache License 2.0
•3•20•0•0•Updated Jun 25, 2025Jun 25, 2025
HippoRAG
Public
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
Python
•
MIT License
•242•2.6k•18•3•Updated Jun 24, 2025Jun 24, 2025
TravelPlanner
Public
[ICML'24 Spotlight] "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"
planning autonomous-agents large-language-models language-agent
Python
•
MIT License
•59•394•1•0•Updated Jun 14, 2025Jun 14, 2025
LLM4Chem
Public
Official code repo for the paper "LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset"
chemistry molecule ai4science llms
Python
•
MIT License
•13•94•0•0•Updated Jun 9, 2025Jun 9, 2025
ChemMCP
Public
A Chemistry Toolkit that turns your AI assistant into a Chemistry coscientist..
ai chemistry toolkit mcp toolbox ai4science llms ai4chemistry
Python
•
Apache License 2.0
•2•38•0•0•Updated Jun 9, 2025Jun 9, 2025
ScienceAgentBench
Public
[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
bioinformatics geoscience code-generation chemoinformatics task-automation cognitive-neuroscience ai4science large-language-models language-agent
Python
•
MIT License
•14•94•3•1•Updated Jun 7, 2025Jun 7, 2025
ChemToolAgent
Public
Official code repo for the paper "ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving" (previously "Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving")
agent chemistry llms
Python
•
MIT License
•5•14•0•0•Updated Jun 7, 2025Jun 7, 2025
AgentSafety
Public
6•99•0•1•Updated May 3, 2025May 3, 2025
InsightAgent
Public
Code & Data for "Completing A Systematic Review in Hours instead of Months with Interactive AI Agents"
Python
•
MIT License
•1•13•1•0•Updated Apr 22, 2025Apr 22, 2025
hal-harness
Public
Python
•17•0•0•0•Updated Apr 20, 2025Apr 20, 2025
SkillWeaver
Public
SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.
Python
•
MIT License
•9•91•0•0•Updated Apr 14, 2025Apr 14, 2025
WebDreamer
Public
"Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents"
Python
•5•78•3•0•Updated Apr 9, 2025Apr 9, 2025
Mind2Web
Public
[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents
Jupyter Notebook
•
MIT License
•112•851•6•6•Updated Apr 3, 2025Apr 3, 2025
reversal-curse-binding
Public
Python
•2•23•1•0•Updated Apr 3, 2025Apr 3, 2025
COSMO
Public
[CIKM'24] Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs
species-classification animal-ecology multimodal-knowledge-graph
Python
•
MIT License
•0•11•0•0•Updated Apr 2, 2025Apr 2, 2025
In-Context-Reranking
Public
[ICLR'25] "Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers"
Python
•
MIT License
•1•28•0•0•Updated Mar 31, 2025Mar 31, 2025
LLM-Planner
Public
[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
C
•
MIT License
•22•194•1•0•Updated Mar 26, 2025Mar 26, 2025
KG-R3
Public
Code for the CIKM'23 paper "A Retrieve-and-Read Framework for Knowledge Graph Link Prediction"
Python
•
MIT License
•0•12•0•0•Updated Mar 23, 2025Mar 23, 2025
GroundCocoa
Public
Python
•0•5•0•0•Updated Feb 27, 2025Feb 27, 2025
MagicBrush
Public
[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".
image-editing image-generation text-to-image image-synthesis text-to-image-synthesis diffusion-models instruction-following text-to-image-generation
Python
•
Other
•14•372•0•0•Updated Feb 20, 2025Feb 20, 2025
SeeAct
Public
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
agent
Python
•
Other
•99•766•11•1•Updated Feb 3, 2025Feb 3, 2025